• artificial intelligence
• coordinated behavior
• disinformation
• social media
• social network

Coordination is a fundamental aspect of life. The advent of social media has made it integral also to online human interactions, such as those that characterize thriving online communities and social movements. At the same time, coordination is also core to effective disinformation, manipulation, and hate campaigns. This thesis has advanced the study of coordinated online behavior by addressing its definition, detection, and characterization across diverse contexts and modalities. We proposed a novel conceptual framework that reconciles existing definitions, providing a comprehensive lens to study coordination. Our work demonstrated the importance of multimodal analysis, emphasizing how the integration of diverse user actions provides a more nuanced understanding of coordination. We designed, developed and evaluated innovative methods for detecting coordinated behavior, including those tailored for detecting botnets and investigating malicious influence operations. Through the use of multiplex networks and unsupervised machine learning approaches, we highlighted the value of modeling multimodal interactions, showing that such approaches outperform traditional monomodal methods in uncovering coordinated activity. Despite these advancements, challenges remain. The scarcity of labeled data, limitations in existing datasets, and restricted access to platform data constrain the development of new methods and their evaluation.
In sum, this thesis contributes a robust foundation for studying coordinated behavior, providing tools, insights, and directions for future research. By addressing the complex nature of coordination, we hope to empower scholars, practitioners, and policymakers to better understand and mitigate the risks associated with coordinated online behavior.